Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wanting
    0.40
     dobbiamo
    0.39
     vogliamo
    0.38
     hicimos
    0.38
     queremos
    0.37
     আমাদের
    0.36
     conosco
    0.34
     farlo
    0.34
    हमें
    0.33
    mene
    0.33
    POSITIVE LOGITS
    StringBuilder
    0.30
    與
    0.29
    ită
    0.26
    솟
    0.26
    สู่
    0.25
    และการ
    0.25
    CONTROL
    0.24
    所の
    0.24
    នៃ
    0.24
    ならでは
    0.24
    Act Density 0.000%

    No Known Activations